Redeploying Claude Fable 5
…We therefore deliberately set the safety classifiers to trigger on a set of requests that we know are likely benign. This “safety margin” approach means that a request has to look very…
Search
People also ask
What safety risks?
If you’re willing to entertain the views outlined above, then it’s not very hard to argue that AI could be a risk to our safety and security. There are two common sense reasons to be concerned. First, it may be tricky to build safe, reliable, and steerable systems when those systems are starting to become as intelligent and as aware of their surroundings as their designers. To use an analogy, it is easy for a chess grandmaster to detect bad moves in a novice but very hard for a novice to detect bad moves in a grandmaster. If we build an AI system that’s significantly more competent than human
Core views on AI safety: When, why, what, and howIntroducing Claude Opus 4.7
…Safety and alignment Overall, Opus 4.7 shows a similar safety profile to Opus 4.6: our evaluations show low rates of concerning behavior such as deception, sycophancy, and cooperation with misuse…
Claude Fable 5 and Claude Mythos 5
…The assessment is described in full, along with a detailed suite of other safety and capabilities tests, in the model’s system card . Early feedback for Claude Fable 5 Customers with early…
Next-generation Constitutional Classifiers: More efficient protection against universal jailbreaks
…Related content Making Claude a chemist Coding agents in the social sciences Results from a survey of 1,260 social scientists about AI and coding agent use. Project Glasswing: An initial update…
Mapping AI-enabled cyber threats: Insights from the LLM ATT&CK Navigator
…Related content Agentic coding and persistent returns to expertise Paving the way for agents in biology Measuring LLMs’ impact on N-day exploits In cybersecurity, a large fraction of real-world harm…
2028: Two scenarios for global AI leadership
…While increasing numbers of researchers in China’s AI labs and policy community are concerned with AI safety risks, this trend has not translated into safety practices on par with labs in…
Scaling Managed Agents: Decoupling the brain from the hands
Engineering at Anthropic Scaling Managed Agents: Decoupling the brain from the hands Get started with Claude Managed Agents by following our docs . A running topic on the Engineering Blog is how to…
The Long-Term Benefit Trust
…Paul Christiano stepped down in April 2024 to take a new role as the Head of AI Safety at the U.S. AI Safety Institute . In January 2026, Kanika Bahl stepped down…
More details on Fable 5’s cyber safeguards and our jailbreak framework
…the “safety margin” that we use to minimize the number of high-risk dual use prompts that are let through. Nevertheless, we do not consider this category to be highly concerning. It…
Building Effective AI Agents
Discover how Anthropic approaches the development of reliable AI agents. Learn about our research on agent capabilities, safety considerations, and technical framework for building trustworthy AI.